skhynix/memflow
Developer tools이 페이지는 AI로 자동 번역되었습니다. 기술적인 세부 사항은 원문을 확인하세요. 원문 보기
Procedural Memory layer for AI agents
개요
MemFlow finds relevant skills for your task in Claude Code. Register your SKILL.md files, then describe your task as usual. MemFlow searches your skills and gives Claude a short list of matches to read through MCP. The current workflow uses Qdrant and an OpenAI-compatible embedding service. You do not need a separate generation LLM. MemFlow stores and serves the SKILL.md text; accompanying scripts and reference files are not included. You need Python 3.10+, uv 0.12.24, Claude Code, and Docker with Compose. You also need an existing OpenAI-compatible embedding service. The commands work in a Linux/macOS shell. uv tool install makes memflow available from any project. If uv reports that its executable directory is missing from your PATH, run uv tool update-shell and open a new terminal. See uv's tool installation guide. Qdrant runs at http://localhost:6333 and keeps its data in scripts/qdrant_data/. If you already have Qdrant, skip the Docker command and use your server's URL below.
README
원문 README의 일부입니다. 원문 보기.
MemFlow
MemFlow retrieves relevant stored skills for a task in Claude Code. Its plugin
injects a short catalog of matches, then Claude reads a selected SKILL.md by
exact ID through MCP. Registration stores the entire skill root in Qdrant. Each
read restores the latest file set into a new local directory, while returning
only the Markdown and small metadata fields. Stored skills retain their trust
state.
Install the Claude Code plugin
Install uv 0.12.24 and
use Claude Code 2.1.220 or later. You need an existing Qdrant service and an
OpenAI-compatible embedding endpoint. MemFlow does not provision these services.
The plugin prepares its own managed Python 3.12 and dependencies; users do not
clone MemFlow, install a Python package, or create a project .env.
Enter these commands in the Claude Code prompt:
/plugin marketplace add skhynix/MemFlow
/plugin install memflow@memflow-plugins
Select user scope and complete Claude’s plugin configuration form. Connection settings are shared across your projects.
| Configuration field | Value |
|---|---|
| Use system certificates during installation | Defaults to off. Enable for runtime downloads through a corporate CA trusted by the operating system |
| Qdrant URL | Existing HTTP(S) service endpoint |
| Collection | Defaults to memflow_skills |
| Qdrant API key | Optional; leave empty for unauthenticated access |
| Embedding API base URL | OpenAI-compatible base URL; MemFlow appends /embeddings |
| Embedding model | Model identifier served by your endpoint |
| Embedding dimensions | Positive integer output dimension |
| Embedding API key | Optional; leave empty to omit the Authorization header |
URLs cannot embed credentials or query strings. Use /plugin configure to select
MemFlow and edit these settings. Credentials stay in Claude-managed configuration
and process memory. The plugin does not read .env or inherit SDK connection,
hybrid, or reranker tuning variables. No /memflow:setup command is required.
Start a fresh Claude session after installation. Both the startup hook and MCP
launcher ensure the runtime is ready before using it, with an installation lock
and a 600-second preparation deadline. MCP connects automatically when preparation
and server initialization finish within Claude’s startup window (30 seconds by
default). A longer first download can exceed that window while the startup hook
continues preparation. Once /memflow:status reports Runtime ready, reconnect
MemFlow in /mcp. Claude can cache a failed connection across restarts, so restarting
alone may not reconnect it. Runtime ready and MCP connected are separate states.
If your network uses a corporate certificate authority already trusted by the
operating system, enable Use system certificates during installation in
MemFlow’s /plugin configure form. Then start a fresh session with the ordinary
추천 도구
다른 키워드를 입력하거나 필터를 제거해 보세요.
설치
npx skillfish add skhynix/memflow